Neural Summarization by Extracting Sentences and Words

Cheng, Jianpeng; Lapata, Mirella

doi:10.18653/v1/p16-1046

Cited by 681 publications

(675 citation statements)

References 24 publications

Supporting

Mentioning

660

Contrasting

Unclassified

Order By: Relevance

“…In Table 3 we compare our method with the results of state-of-the-art neural summarization methods reported in recent papers. Extractive models include NN-SE (Cheng and Lapata, 2016) and SummaRuNNer (Nallapati et al, 2017), while SummaRuNNer-abs is also an extractive model similar to SummaRuNNer but is trained directly on the abstractive summaries. Moreover, we include several baselines for comparison, including the baselines reported in (Cheng and Lapata, 2016) although they are tested on 500 samples of the test set.…”

Section: Discussionmentioning

confidence: 99%

Abstractive Document Summarization with a Graph-Based Attentional Neural Model

Tan¹,

Wan²,

Xiao³

2017

Proceedings of the 55th Annual Meeting of the Association For Computational Linguistics (Volume 1: Long Papers)

301

257

View full text Add to dashboard Cite

Abstractive summarization is the ultimate goal of document summarization research, but previously it is less investigated due to the immaturity of text generation techniques. Recently impressive progress has been made to abstractive sentence summarization using neural models. Unfortunately, attempts on abstractive document summarization are still in a primitive stage, and the evaluation results are worse than extractive methods on benchmark datasets. In this paper, we review the difficulties of neural abstractive document summarization, and propose a novel graph-based attention mechanism in the sequence-to-sequence framework. The intuition is to address the saliency factor of summarization, which has been overlooked by prior works. Experimental results demonstrate our model is able to achieve considerable improvement over previous neural abstractive models. The data-driven neural abstractive method is also competitive with state-of-the-art extractive methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Abstractive Document Summarization with a Graph-Based Attentional Neural Model

Tan¹,

Wan²,

Xiao³

2017

Proceedings of the 55th Annual Meeting of the Association For Computational Linguistics (Volume 1: Long Papers)

301

257

View full text Add to dashboard Cite

show abstract

“…The hyper parameters were optimized using grid search. We extracted three sentences with the highest scores in the manner described in an earlier report (Cheng and Lapata, 2016).…”

Section: Implementation Detailsmentioning

confidence: 99%

“…Although we employ an encoder-decoder architecture in the predictor component of our summarization framework, the framework can be applied to all models of sentence extraction using distributed representation as inputs, including recently advanced other attention-based encoder-decoder networks (Wang et al, 2016;Yang et al, 2016) (Cheng and Lapata, 2016;Nallapati et al, 2017) argue that a stumbling block to applying neural network models to extractive summarization is the lack of training data and documents with sentences labeled as summary-worthy. To overcome this, several studies have used artificial reference summaries (Sun et al, 2005;Svore et al, 2007;Woodsend and Lapata, 2010;Cheng and Lapata, 2016) compiled by collecting documents and corresponding highlights from other sources. However, preparing such a parallel corpus often requires domain-specific or expert knowledge depending on the domain (Filippova et al, 2009;Parveen et al, 2016).…”

Section: Related Workmentioning

confidence: 99%

“…Extractive summarization approaches based on neural network-based approaches (Kågebäck et al, 2014;Cao et al, 2015;Yin and Pei, 2015;Cao et al, 2016) have advanced rapidly. Recently, an attentional encoderdecoder for extractive single-document summarization was proposed and its application to the news corpus was demonstrated (Cheng and Lapata, 2016;Nallapati et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

“…The reference summaries are manually or semiautomatically created in advance. Some existing studies employ parallel corpora as artificial reference summaries (Woodsend and Lapata, 2010;Cheng and Lapata, 2016). However, preparing such large volumes of reference summaries manually is sometimes costly.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Extractive Summarization Using Multi-Task Learning with Document Classification

Isonuma¹,

Fujino²,

Mori³

et al. 2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

The need for automatic document summarization that can be used for practical applications is increasing rapidly. In this paper, we propose a general framework for summarization that extracts sentences from a document using externally related information. Our work is aimed at single document summarization using small amounts of reference summaries. In particular, we address document summarization in the framework of multitask learning using curriculum learning for sentence extraction and document classification. The proposed framework enables us to obtain better feature representations to extract sentences from documents. We evaluate our proposed summarization method on two datasets: financial report and news corpus. Experimental results demonstrate that our summarizers achieve performance that is comparable to stateof-the-art systems.

show abstract

EcForest: Extractive document summarization through enhanced sentence embedding and cascade forest

Yang

Al-Sabahi

et al. 2019

Concurrency and Computation

View full text Add to dashboard Cite

We present EcForest, an extractive summarization model through Enhanced Sentence Embedding and Cascade Forest. Sentence representation is of great significance for many summarization methods. Bag-of-words mostly fails to grasp the semantics, and typical embedding models cannot capture more complex semantic features, such as polysemy and the meaning of a phrase, which is usually ignored by simply averaging the word embeddings included in a sentence. To this end, we propose Enhanced Sentence Embedding (ESE) model to solve such drawbacks via mapping several valid features to dense vectors. Essentially, the enhanced sentence embedding is a novel model for improving the distributed representation of sentence. Our sentence embedding model is universally applicable and it can be adapted to other NLP tasks. Moreover, deep forest is used as a sentence extraction algorithm for its robustness to the hyper-parameters and its efficient training algorithm compared to deep neural network.The evaluation of variant models proposed in this work proves the validation of the enhanced sentence embedding. The comparison results between EcForest and several baselines on two different datasets demonstrate that the proposed summarization model performs better than or with high competitiveness to the state-of-the-art.

show abstract

Neural Summarization by Extracting Sentences and Words

Cited by 681 publications

References 24 publications

Abstractive Document Summarization with a Graph-Based Attentional Neural Model

Abstractive Document Summarization with a Graph-Based Attentional Neural Model

Extractive Summarization Using Multi-Task Learning with Document Classification

EcForest: Extractive document summarization through enhanced sentence embedding and cascade forest

Contact Info

Product

Resources

About